2016/11/14 by Chengzhe Yan, Jie Hu, Yan, Chengzhe +3
Computer Science · #Handwritten Text Recognition Techniques #Image Processing and 3D Reconstruction #Generative Adversarial Networks and Image Synthesis
paper · pdf · doi:10.48550/arxiv.1611.04298
In this paper, a novel neural network architecture is proposed attempting to rectify text images with mild assumptions. A new dataset of text images is collected to verify our model and open to public. We explored the capability of deep neural network in learning geometric transformation and found the model could segment the text image without explicit supervised segmentation information. Experiments show the architecture proposed can restore planar transformations with wonderful robustness and effectiveness.